feat(antigravity): comprehensive enhancements - model mapping, rate limiting, scheduling & ops

Key changes:
- Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching
- Unified rate limiting: scope-level → model-level with Redis snapshot sync
- Load-balanced scheduling by call count with smart retry mechanism
- Force cache billing support
- Model identity injection in prompts with leak prevention
- Thinking mode auto-handling (max_tokens/budget_tokens fix)
- Frontend: whitelist mode toggle, model mapping validation, status indicators
- Gemini session fallback with Redis Trie O(L) matching
- Ops: enhanced concurrency monitoring, account availability, retry logic
- Migration scripts: 049-051 for model mapping unification

backend/internal/service/gateway_request.go

@@ -4,6 +4,8 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+
+	"github.com/Wei-Shaw/sub2api/internal/pkg/antigravity"
 )
 
 // ParsedRequest 保存网关请求的预解析结果
@@ -19,13 +21,14 @@ import (
 // 2. 将解析结果 ParsedRequest 传递给 Service 层
 // 3. 避免重复 json.Unmarshal，减少 CPU 和内存开销
 type ParsedRequest struct {
-	Body           []byte // 原始请求体（保留用于转发）
-	Model          string // 请求的模型名称
-	Stream         bool   // 是否为流式请求
-	MetadataUserID string // metadata.user_id（用于会话亲和）
-	System         any    // system 字段内容
-	Messages       []any  // messages 数组
-	HasSystem      bool   // 是否包含 system 字段（包含 null 也视为显式传入）
+	Body            []byte // 原始请求体（保留用于转发）
+	Model           string // 请求的模型名称
+	Stream          bool   // 是否为流式请求
+	MetadataUserID  string // metadata.user_id（用于会话亲和）
+	System          any    // system 字段内容
+	Messages        []any  // messages 数组
+	HasSystem       bool   // 是否包含 system 字段（包含 null 也视为显式传入）
+	ThinkingEnabled bool   // 是否开启 thinking（部分平台会影响最终模型名）
 }
 
 // ParseGatewayRequest 解析网关请求体并返回结构化结果
@@ -69,6 +72,13 @@ func ParseGatewayRequest(body []byte) (*ParsedRequest, error) {
 		parsed.Messages = messages
 	}
 
+	// thinking: {type: "enabled"}
+	if rawThinking, ok := req["thinking"].(map[string]any); ok {
+		if t, ok := rawThinking["type"].(string); ok && t == "enabled" {
+			parsed.ThinkingEnabled = true
+		}
+	}
+
 	return parsed, nil
 }
 
@@ -466,7 +476,7 @@ func filterThinkingBlocksInternal(body []byte, _ bool) []byte {
 				// only keep thinking blocks with valid signatures
 				if thinkingEnabled && role == "assistant" {
 					signature, _ := blockMap["signature"].(string)
-					if signature != "" && signature != "skip_thought_signature_validator" {
+					if signature != "" && signature != antigravity.DummyThoughtSignature {
 						newContent = append(newContent, block)
 						continue
 					}